linux/mm/page-writeback.c

1039 lines
29 KiB
C
Raw Normal View History

/*
* mm/page-writeback.c
*
* Copyright (C) 2002, Linus Torvalds.
*
* Contains functions related to writing back dirty pages at the
* address_space level.
*
* 10Apr2002 akpm@zip.com.au
* Initial version
*/
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/spinlock.h>
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/swap.h>
#include <linux/slab.h>
#include <linux/pagemap.h>
#include <linux/writeback.h>
#include <linux/init.h>
#include <linux/backing-dev.h>
#include <linux/task_io_accounting_ops.h>
#include <linux/blkdev.h>
#include <linux/mpage.h>
[PATCH] mm: tracking shared dirty pages Tracking of dirty pages in shared writeable mmap()s. The idea is simple: write protect clean shared writeable pages, catch the write-fault, make writeable and set dirty. On page write-back clean all the PTE dirty bits and write protect them once again. The implementation is a tad harder, mainly because the default backing_dev_info capabilities were too loosely maintained. Hence it is not enough to test the backing_dev_info for cap_account_dirty. The current heuristic is as follows, a VMA is eligible when: - its shared writeable (vm_flags & (VM_WRITE|VM_SHARED)) == (VM_WRITE|VM_SHARED) - it is not a 'special' mapping (vm_flags & (VM_PFNMAP|VM_INSERTPAGE)) == 0 - the backing_dev_info is cap_account_dirty mapping_cap_account_dirty(vma->vm_file->f_mapping) - f_op->mmap() didn't change the default page protection Page from remap_pfn_range() are explicitly excluded because their COW semantics are already horrid enough (see vm_normal_page() in do_wp_page()) and because they don't have a backing store anyway. mprotect() is taught about the new behaviour as well. However it overrides the last condition. Cleaning the pages on write-back is done with page_mkclean() a new rmap call. It can be called on any page, but is currently only implemented for mapped pages, if the page is found the be of a VMA that accounts dirty pages it will also wrprotect the PTE. Finally, in fs/buffers.c:try_to_free_buffers(); remove clear_page_dirty() from under ->private_lock. This seems to be safe, since ->private_lock is used to serialize access to the buffers, not the page itself. This is needed because clear_page_dirty() will call into page_mkclean() and would thereby violate locking order. [dhowells@redhat.com: Provide a page_mkclean() implementation for NOMMU] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Hugh Dickins <hugh@veritas.com> Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-09-26 06:30:57 +00:00
#include <linux/rmap.h>
#include <linux/percpu.h>
#include <linux/notifier.h>
#include <linux/smp.h>
#include <linux/sysctl.h>
#include <linux/cpu.h>
#include <linux/syscalls.h>
#include <linux/buffer_head.h>
#include <linux/pagevec.h>
/*
* The maximum number of pages to writeout in a single bdflush/kupdate
* operation. We do this so we don't hold I_LOCK against an inode for
* enormous amounts of time, which would block a userspace task which has
* been forced to throttle against that inode. Also, the code reevaluates
* the dirty each time it has written this many pages.
*/
#define MAX_WRITEBACK_PAGES 1024
/*
* After a CPU has dirtied this many pages, balance_dirty_pages_ratelimited
* will look to see if it needs to force writeback or throttling.
*/
static long ratelimit_pages = 32;
static int dirty_exceeded __cacheline_aligned_in_smp; /* Dirty mem may be over limit */
/*
* When balance_dirty_pages decides that the caller needs to perform some
* non-background writeback, this is how many pages it will attempt to write.
* It should be somewhat larger than RATELIMIT_PAGES to ensure that reasonably
* large amounts of I/O are submitted.
*/
static inline long sync_writeback_pages(void)
{
return ratelimit_pages + ratelimit_pages / 2;
}
/* The following parameters are exported via /proc/sys/vm */
/*
* Start background writeback (via pdflush) at this percentage
*/
int dirty_background_ratio = 5;
/*
* The generator of dirty data starts writeback at this percentage
*/
int vm_dirty_ratio = 10;
/*
* The interval between `kupdate'-style writebacks, in jiffies
*/
int dirty_writeback_interval = 5 * HZ;
/*
* The longest number of jiffies for which data is allowed to remain dirty
*/
int dirty_expire_interval = 30 * HZ;
/*
* Flag that makes the machine dump writes/reads and block dirtyings.
*/
int block_dump;
/*
* Flag that puts the machine in "laptop mode". Doubles as a timeout in jiffies:
* a full sync is triggered after this time elapses without any disk activity.
*/
int laptop_mode;
EXPORT_SYMBOL(laptop_mode);
/* End of sysctl-exported parameters */
static void background_writeout(unsigned long _min_pages);
/*
* Work out the current dirty-memory clamping and background writeout
* thresholds.
*
* The main aim here is to lower them aggressively if there is a lot of mapped
* memory around. To avoid stressing page reclaim with lots of unreclaimable
* pages. It is better to clamp down on writers than to start swapping, and
* performing lots of scanning.
*
* We only allow 1/2 of the currently-unmapped memory to be dirtied.
*
* We don't permit the clamping level to fall below 5% - that is getting rather
* excessive.
*
* We make sure that the background writeout level is below the adjusted
* clamping level.
*/
static unsigned long highmem_dirtyable_memory(unsigned long total)
{
#ifdef CONFIG_HIGHMEM
int node;
unsigned long x = 0;
for_each_online_node(node) {
struct zone *z =
&NODE_DATA(node)->node_zones[ZONE_HIGHMEM];
x += zone_page_state(z, NR_FREE_PAGES)
+ zone_page_state(z, NR_INACTIVE)
+ zone_page_state(z, NR_ACTIVE);
}
/*
* Make sure that the number of highmem pages is never larger
* than the number of the total dirtyable memory. This can only
* occur in very strange VM situations but we want to make sure
* that this does not occur.
*/
return min(x, total);
#else
return 0;
#endif
}
static unsigned long determine_dirtyable_memory(void)
{
unsigned long x;
x = global_page_state(NR_FREE_PAGES)
+ global_page_state(NR_INACTIVE)
+ global_page_state(NR_ACTIVE);
x -= highmem_dirtyable_memory(x);
return x + 1; /* Ensure that we never return 0 */
}
static void
get_dirty_limits(long *pbackground, long *pdirty,
struct address_space *mapping)
{
int background_ratio; /* Percentages */
int dirty_ratio;
int unmapped_ratio;
long background;
long dirty;
unsigned long available_memory = determine_dirtyable_memory();
struct task_struct *tsk;
unmapped_ratio = 100 - ((global_page_state(NR_FILE_MAPPED) +
global_page_state(NR_ANON_PAGES)) * 100) /
available_memory;
dirty_ratio = vm_dirty_ratio;
if (dirty_ratio > unmapped_ratio / 2)
dirty_ratio = unmapped_ratio / 2;
if (dirty_ratio < 5)
dirty_ratio = 5;
background_ratio = dirty_background_ratio;
if (background_ratio >= dirty_ratio)
background_ratio = dirty_ratio / 2;
background = (background_ratio * available_memory) / 100;
dirty = (dirty_ratio * available_memory) / 100;
tsk = current;
if (tsk->flags & PF_LESS_THROTTLE || rt_task(tsk)) {
background += background / 4;
dirty += dirty / 4;
}
*pbackground = background;
*pdirty = dirty;
}
/*
* balance_dirty_pages() must be called by processes which are generating dirty
* data. It looks at the number of dirty pages in the machine and will force
* the caller to perform writeback if the system is over `vm_dirty_ratio'.
* If we're over `background_thresh' then pdflush is woken to perform some
* writeout.
*/
static void balance_dirty_pages(struct address_space *mapping)
{
long nr_reclaimable;
long background_thresh;
long dirty_thresh;
unsigned long pages_written = 0;
unsigned long write_chunk = sync_writeback_pages();
struct backing_dev_info *bdi = mapping->backing_dev_info;
for (;;) {
struct writeback_control wbc = {
.bdi = bdi,
.sync_mode = WB_SYNC_NONE,
.older_than_this = NULL,
.nr_to_write = write_chunk,
[PATCH] writeback: fix range handling When a writeback_control's `start' and `end' fields are used to indicate a one-byte-range starting at file offset zero, the required values of .start=0,.end=0 mean that the ->writepages() implementation has no way of telling that it is being asked to perform a range request. Because we're currently overloading (start == 0 && end == 0) to mean "this is not a write-a-range request". To make all this sane, the patch changes range of writeback_control. So caller does: If it is calling ->writepages() to write pages, it sets range (range_start/end or range_cyclic) always. And if range_cyclic is true, ->writepages() thinks the range is cyclic, otherwise it just uses range_start and range_end. This patch does, - Add LLONG_MAX, LLONG_MIN, ULLONG_MAX to include/linux/kernel.h -1 is usually ok for range_end (type is long long). But, if someone did, range_end += val; range_end is "val - 1" u64val = range_end >> bits; u64val is "~(0ULL)" or something, they are wrong. So, this adds LLONG_MAX to avoid nasty things, and uses LLONG_MAX for range_end. - All callers of ->writepages() sets range_start/end or range_cyclic. - Fix updates of ->writeback_index. It seems already bit strange. If it starts at 0 and ended by check of nr_to_write, this last index may reduce chance to scan end of file. So, this updates ->writeback_index only if range_cyclic is true or whole-file is scanned. Signed-off-by: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp> Cc: Nathan Scott <nathans@sgi.com> Cc: Anton Altaparmakov <aia21@cantab.net> Cc: Steven French <sfrench@us.ibm.com> Cc: "Vladimir V. Saveliev" <vs@namesys.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 09:03:26 +00:00
.range_cyclic = 1,
};
get_dirty_limits(&background_thresh, &dirty_thresh, mapping);
nr_reclaimable = global_page_state(NR_FILE_DIRTY) +
global_page_state(NR_UNSTABLE_NFS);
if (nr_reclaimable + global_page_state(NR_WRITEBACK) <=
dirty_thresh)
break;
if (!dirty_exceeded)
dirty_exceeded = 1;
/* Note: nr_reclaimable denotes nr_dirty + nr_unstable.
* Unstable writes are a feature of certain networked
* filesystems (i.e. NFS) in which data may have been
* written to the server's write cache, but has not yet
* been flushed to permanent storage.
*/
if (nr_reclaimable) {
writeback_inodes(&wbc);
get_dirty_limits(&background_thresh,
&dirty_thresh, mapping);
nr_reclaimable = global_page_state(NR_FILE_DIRTY) +
global_page_state(NR_UNSTABLE_NFS);
if (nr_reclaimable +
global_page_state(NR_WRITEBACK)
<= dirty_thresh)
break;
pages_written += write_chunk - wbc.nr_to_write;
if (pages_written >= write_chunk)
break; /* We've done our duty */
}
congestion_wait(WRITE, HZ/10);
}
if (nr_reclaimable + global_page_state(NR_WRITEBACK)
<= dirty_thresh && dirty_exceeded)
dirty_exceeded = 0;
if (writeback_in_progress(bdi))
return; /* pdflush is already working this queue */
/*
* In laptop mode, we wait until hitting the higher threshold before
* starting background writeout, and then write out all the way down
* to the lower threshold. So slow writers cause minimal disk activity.
*
* In normal mode, we start background writeout at the lower
* background_thresh, to keep the amount of dirty memory low.
*/
if ((laptop_mode && pages_written) ||
(!laptop_mode && (nr_reclaimable > background_thresh)))
pdflush_operation(background_writeout, 0);
}
void set_page_dirty_balance(struct page *page, int page_mkwrite)
{
if (set_page_dirty(page) || page_mkwrite) {
struct address_space *mapping = page_mapping(page);
if (mapping)
balance_dirty_pages_ratelimited(mapping);
}
}
/**
* balance_dirty_pages_ratelimited_nr - balance dirty memory state
* @mapping: address_space which was dirtied
* @nr_pages_dirtied: number of pages which the caller has just dirtied
*
* Processes which are dirtying memory should call in here once for each page
* which was newly dirtied. The function will periodically check the system's
* dirty state and will initiate writeback if needed.
*
* On really big machines, get_writeback_state is expensive, so try to avoid
* calling it too often (ratelimiting). But once we're over the dirty memory
* limit we decrease the ratelimiting by a lot, to prevent individual processes
* from overshooting the limit by (ratelimit_pages) each.
*/
void balance_dirty_pages_ratelimited_nr(struct address_space *mapping,
unsigned long nr_pages_dirtied)
{
static DEFINE_PER_CPU(unsigned long, ratelimits) = 0;
unsigned long ratelimit;
unsigned long *p;
ratelimit = ratelimit_pages;
if (dirty_exceeded)
ratelimit = 8;
/*
* Check the rate limiting. Also, we do not want to throttle real-time
* tasks in balance_dirty_pages(). Period.
*/
preempt_disable();
p = &__get_cpu_var(ratelimits);
*p += nr_pages_dirtied;
if (unlikely(*p >= ratelimit)) {
*p = 0;
preempt_enable();
balance_dirty_pages(mapping);
return;
}
preempt_enable();
}
EXPORT_SYMBOL(balance_dirty_pages_ratelimited_nr);
void throttle_vm_writeout(gfp_t gfp_mask)
{
long background_thresh;
long dirty_thresh;
if ((gfp_mask & (__GFP_FS|__GFP_IO)) != (__GFP_FS|__GFP_IO)) {
/*
* The caller might hold locks which can prevent IO completion
* or progress in the filesystem. So we cannot just sit here
* waiting for IO to complete.
*/
congestion_wait(WRITE, HZ/10);
return;
}
for ( ; ; ) {
get_dirty_limits(&background_thresh, &dirty_thresh, NULL);
/*
* Boost the allowable dirty threshold a bit for page
* allocators so they don't get DoS'ed by heavy writers
*/
dirty_thresh += dirty_thresh / 10; /* wheeee... */
if (global_page_state(NR_UNSTABLE_NFS) +
global_page_state(NR_WRITEBACK) <= dirty_thresh)
break;
congestion_wait(WRITE, HZ/10);
}
}
/*
* writeback at least _min_pages, and keep writing until the amount of dirty
* memory is less than the background threshold, or until we're all clean.
*/
static void background_writeout(unsigned long _min_pages)
{
long min_pages = _min_pages;
struct writeback_control wbc = {
.bdi = NULL,
.sync_mode = WB_SYNC_NONE,
.older_than_this = NULL,
.nr_to_write = 0,
.nonblocking = 1,
[PATCH] writeback: fix range handling When a writeback_control's `start' and `end' fields are used to indicate a one-byte-range starting at file offset zero, the required values of .start=0,.end=0 mean that the ->writepages() implementation has no way of telling that it is being asked to perform a range request. Because we're currently overloading (start == 0 && end == 0) to mean "this is not a write-a-range request". To make all this sane, the patch changes range of writeback_control. So caller does: If it is calling ->writepages() to write pages, it sets range (range_start/end or range_cyclic) always. And if range_cyclic is true, ->writepages() thinks the range is cyclic, otherwise it just uses range_start and range_end. This patch does, - Add LLONG_MAX, LLONG_MIN, ULLONG_MAX to include/linux/kernel.h -1 is usually ok for range_end (type is long long). But, if someone did, range_end += val; range_end is "val - 1" u64val = range_end >> bits; u64val is "~(0ULL)" or something, they are wrong. So, this adds LLONG_MAX to avoid nasty things, and uses LLONG_MAX for range_end. - All callers of ->writepages() sets range_start/end or range_cyclic. - Fix updates of ->writeback_index. It seems already bit strange. If it starts at 0 and ended by check of nr_to_write, this last index may reduce chance to scan end of file. So, this updates ->writeback_index only if range_cyclic is true or whole-file is scanned. Signed-off-by: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp> Cc: Nathan Scott <nathans@sgi.com> Cc: Anton Altaparmakov <aia21@cantab.net> Cc: Steven French <sfrench@us.ibm.com> Cc: "Vladimir V. Saveliev" <vs@namesys.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 09:03:26 +00:00
.range_cyclic = 1,
};
for ( ; ; ) {
long background_thresh;
long dirty_thresh;
get_dirty_limits(&background_thresh, &dirty_thresh, NULL);
if (global_page_state(NR_FILE_DIRTY) +
global_page_state(NR_UNSTABLE_NFS) < background_thresh
&& min_pages <= 0)
break;
wbc.encountered_congestion = 0;
wbc.nr_to_write = MAX_WRITEBACK_PAGES;
wbc.pages_skipped = 0;
writeback_inodes(&wbc);
min_pages -= MAX_WRITEBACK_PAGES - wbc.nr_to_write;
if (wbc.nr_to_write > 0 || wbc.pages_skipped > 0) {
/* Wrote less than expected */
congestion_wait(WRITE, HZ/10);
if (!wbc.encountered_congestion)
break;
}
}
}
/*
* Start writeback of `nr_pages' pages. If `nr_pages' is zero, write back
* the whole world. Returns 0 if a pdflush thread was dispatched. Returns
* -1 if all pdflush threads were busy.
*/
int wakeup_pdflush(long nr_pages)
{
if (nr_pages == 0)
nr_pages = global_page_state(NR_FILE_DIRTY) +
global_page_state(NR_UNSTABLE_NFS);
return pdflush_operation(background_writeout, nr_pages);
}
static void wb_timer_fn(unsigned long unused);
static void laptop_timer_fn(unsigned long unused);
static DEFINE_TIMER(wb_timer, wb_timer_fn, 0, 0);
static DEFINE_TIMER(laptop_mode_wb_timer, laptop_timer_fn, 0, 0);
/*
* Periodic writeback of "old" data.
*
* Define "old": the first time one of an inode's pages is dirtied, we mark the
* dirtying-time in the inode's address_space. So this periodic writeback code
* just walks the superblock inode list, writing back any inodes which are
* older than a specific point in time.
*
* Try to run once per dirty_writeback_interval. But if a writeback event
* takes longer than a dirty_writeback_interval interval, then leave a
* one-second gap.
*
* older_than_this takes precedence over nr_to_write. So we'll only write back
* all dirty pages if they are all attached to "old" mappings.
*/
static void wb_kupdate(unsigned long arg)
{
unsigned long oldest_jif;
unsigned long start_jif;
unsigned long next_jif;
long nr_to_write;
struct writeback_control wbc = {
.bdi = NULL,
.sync_mode = WB_SYNC_NONE,
.older_than_this = &oldest_jif,
.nr_to_write = 0,
.nonblocking = 1,
.for_kupdate = 1,
[PATCH] writeback: fix range handling When a writeback_control's `start' and `end' fields are used to indicate a one-byte-range starting at file offset zero, the required values of .start=0,.end=0 mean that the ->writepages() implementation has no way of telling that it is being asked to perform a range request. Because we're currently overloading (start == 0 && end == 0) to mean "this is not a write-a-range request". To make all this sane, the patch changes range of writeback_control. So caller does: If it is calling ->writepages() to write pages, it sets range (range_start/end or range_cyclic) always. And if range_cyclic is true, ->writepages() thinks the range is cyclic, otherwise it just uses range_start and range_end. This patch does, - Add LLONG_MAX, LLONG_MIN, ULLONG_MAX to include/linux/kernel.h -1 is usually ok for range_end (type is long long). But, if someone did, range_end += val; range_end is "val - 1" u64val = range_end >> bits; u64val is "~(0ULL)" or something, they are wrong. So, this adds LLONG_MAX to avoid nasty things, and uses LLONG_MAX for range_end. - All callers of ->writepages() sets range_start/end or range_cyclic. - Fix updates of ->writeback_index. It seems already bit strange. If it starts at 0 and ended by check of nr_to_write, this last index may reduce chance to scan end of file. So, this updates ->writeback_index only if range_cyclic is true or whole-file is scanned. Signed-off-by: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp> Cc: Nathan Scott <nathans@sgi.com> Cc: Anton Altaparmakov <aia21@cantab.net> Cc: Steven French <sfrench@us.ibm.com> Cc: "Vladimir V. Saveliev" <vs@namesys.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 09:03:26 +00:00
.range_cyclic = 1,
};
sync_supers();
oldest_jif = jiffies - dirty_expire_interval;
start_jif = jiffies;
next_jif = start_jif + dirty_writeback_interval;
nr_to_write = global_page_state(NR_FILE_DIRTY) +
global_page_state(NR_UNSTABLE_NFS) +
(inodes_stat.nr_inodes - inodes_stat.nr_unused);
while (nr_to_write > 0) {
wbc.encountered_congestion = 0;
wbc.nr_to_write = MAX_WRITEBACK_PAGES;
writeback_inodes(&wbc);
if (wbc.nr_to_write > 0) {
if (wbc.encountered_congestion)
congestion_wait(WRITE, HZ/10);
else
break; /* All the old data is written */
}
nr_to_write -= MAX_WRITEBACK_PAGES - wbc.nr_to_write;
}
if (time_before(next_jif, jiffies + HZ))
next_jif = jiffies + HZ;
if (dirty_writeback_interval)
mod_timer(&wb_timer, next_jif);
}
/*
* sysctl handler for /proc/sys/vm/dirty_writeback_centisecs
*/
int dirty_writeback_centisecs_handler(ctl_table *table, int write,
struct file *file, void __user *buffer, size_t *length, loff_t *ppos)
{
proc_dointvec_userhz_jiffies(table, write, file, buffer, length, ppos);
if (dirty_writeback_interval)
mod_timer(&wb_timer, jiffies + dirty_writeback_interval);
else
del_timer(&wb_timer);
return 0;
}
static void wb_timer_fn(unsigned long unused)
{
if (pdflush_operation(wb_kupdate, 0) < 0)
mod_timer(&wb_timer, jiffies + HZ); /* delay 1 second */
}
static void laptop_flush(unsigned long unused)
{
sys_sync();
}
static void laptop_timer_fn(unsigned long unused)
{
pdflush_operation(laptop_flush, 0);
}
/*
* We've spun up the disk and we're in laptop mode: schedule writeback
* of all dirty data a few seconds from now. If the flush is already scheduled
* then push it back - the user is still using the disk.
*/
void laptop_io_completion(void)
{
mod_timer(&laptop_mode_wb_timer, jiffies + laptop_mode);
}
/*
* We're in laptop mode and we've just synced. The sync's writes will have
* caused another writeback to be scheduled by laptop_io_completion.
* Nothing needs to be written back anymore, so we unschedule the writeback.
*/
void laptop_sync_completion(void)
{
del_timer(&laptop_mode_wb_timer);
}
/*
* If ratelimit_pages is too high then we can get into dirty-data overload
* if a large number of processes all perform writes at the same time.
* If it is too low then SMP machines will call the (expensive)
* get_writeback_state too often.
*
* Here we set ratelimit_pages to a level which ensures that when all CPUs are
* dirtying in parallel, we cannot go more than 3% (1/32) over the dirty memory
* thresholds before writeback cuts in.
*
* But the limit should not be set too high. Because it also controls the
* amount of memory which the balance_dirty_pages() caller has to write back.
* If this is too large then the caller will block on the IO queue all the
* time. So limit it to four megabytes - the balance_dirty_pages() caller
* will write six megabyte chunks, max.
*/
void writeback_set_ratelimit(void)
{
ratelimit_pages = vm_total_pages / (num_online_cpus() * 32);
if (ratelimit_pages < 16)
ratelimit_pages = 16;
if (ratelimit_pages * PAGE_CACHE_SIZE > 4096 * 1024)
ratelimit_pages = (4096 * 1024) / PAGE_CACHE_SIZE;
}
static int __cpuinit
ratelimit_handler(struct notifier_block *self, unsigned long u, void *v)
{
writeback_set_ratelimit();
return NOTIFY_DONE;
}
static struct notifier_block __cpuinitdata ratelimit_nb = {
.notifier_call = ratelimit_handler,
.next = NULL,
};
/*
* Called early on to tune the page writeback dirty limits.
*
* We used to scale dirty pages according to how total memory
* related to pages that could be allocated for buffers (by
* comparing nr_free_buffer_pages() to vm_total_pages.
*
* However, that was when we used "dirty_ratio" to scale with
* all memory, and we don't do that any more. "dirty_ratio"
* is now applied to total non-HIGHPAGE memory (by subtracting
* totalhigh_pages from vm_total_pages), and as such we can't
* get into the old insane situation any more where we had
* large amounts of dirty pages compared to a small amount of
* non-HIGHMEM memory.
*
* But we might still want to scale the dirty_ratio by how
* much memory the box has..
*/
void __init page_writeback_init(void)
{
mod_timer(&wb_timer, jiffies + dirty_writeback_interval);
writeback_set_ratelimit();
register_cpu_notifier(&ratelimit_nb);
}
/**
* write_cache_pages - walk the list of dirty pages of the given address space and write all of them.
* @mapping: address space structure to write
* @wbc: subtract the number of written pages from *@wbc->nr_to_write
* @writepage: function called for each page
* @data: data passed to writepage function
*
* If a page is already under I/O, write_cache_pages() skips it, even
* if it's dirty. This is desirable behaviour for memory-cleaning writeback,
* but it is INCORRECT for data-integrity system calls such as fsync(). fsync()
* and msync() need to guarantee that all the data which was dirty at the time
* the call was made get new I/O started against them. If wbc->sync_mode is
* WB_SYNC_ALL then we were called for data integrity and we must wait for
* existing IO to complete.
*/
int write_cache_pages(struct address_space *mapping,
struct writeback_control *wbc, writepage_t writepage,
void *data)
{
struct backing_dev_info *bdi = mapping->backing_dev_info;
int ret = 0;
int done = 0;
struct pagevec pvec;
int nr_pages;
pgoff_t index;
pgoff_t end; /* Inclusive */
int scanned = 0;
int range_whole = 0;
if (wbc->nonblocking && bdi_write_congested(bdi)) {
wbc->encountered_congestion = 1;
return 0;
}
pagevec_init(&pvec, 0);
if (wbc->range_cyclic) {
index = mapping->writeback_index; /* Start from prev offset */
end = -1;
} else {
index = wbc->range_start >> PAGE_CACHE_SHIFT;
end = wbc->range_end >> PAGE_CACHE_SHIFT;
if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
range_whole = 1;
scanned = 1;
}
retry:
while (!done && (index <= end) &&
(nr_pages = pagevec_lookup_tag(&pvec, mapping, &index,
PAGECACHE_TAG_DIRTY,
min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1))) {
unsigned i;
scanned = 1;
for (i = 0; i < nr_pages; i++) {
struct page *page = pvec.pages[i];
/*
* At this point we hold neither mapping->tree_lock nor
* lock on the page itself: the page may be truncated or
* invalidated (changing page->mapping to NULL), or even
* swizzled back from swapper_space to tmpfs file
* mapping
*/
lock_page(page);
if (unlikely(page->mapping != mapping)) {
unlock_page(page);
continue;
}
if (!wbc->range_cyclic && page->index > end) {
done = 1;
unlock_page(page);
continue;
}
if (wbc->sync_mode != WB_SYNC_NONE)
wait_on_page_writeback(page);
if (PageWriteback(page) ||
!clear_page_dirty_for_io(page)) {
unlock_page(page);
continue;
}
ret = (*writepage)(page, wbc, data);
if (unlikely(ret == AOP_WRITEPAGE_ACTIVATE))
unlock_page(page);
if (ret || (--(wbc->nr_to_write) <= 0))
done = 1;
if (wbc->nonblocking && bdi_write_congested(bdi)) {
wbc->encountered_congestion = 1;
done = 1;
}
}
pagevec_release(&pvec);
cond_resched();
}
if (!scanned && !done) {
/*
* We hit the last page and there is more work to be done: wrap
* back to the start of the file
*/
scanned = 1;
index = 0;
goto retry;
}
if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0))
mapping->writeback_index = index;
return ret;
}
EXPORT_SYMBOL(write_cache_pages);
/*
* Function used by generic_writepages to call the real writepage
* function and set the mapping flags on error
*/
static int __writepage(struct page *page, struct writeback_control *wbc,
void *data)
{
struct address_space *mapping = data;
int ret = mapping->a_ops->writepage(page, wbc);
mapping_set_error(mapping, ret);
return ret;
}
/**
* generic_writepages - walk the list of dirty pages of the given address space and writepage() all of them.
* @mapping: address space structure to write
* @wbc: subtract the number of written pages from *@wbc->nr_to_write
*
* This is a library function, which implements the writepages()
* address_space_operation.
*/
int generic_writepages(struct address_space *mapping,
struct writeback_control *wbc)
{
/* deal with chardevs and other special file */
if (!mapping->a_ops->writepage)
return 0;
return write_cache_pages(mapping, wbc, __writepage, mapping);
}
EXPORT_SYMBOL(generic_writepages);
int do_writepages(struct address_space *mapping, struct writeback_control *wbc)
{
int ret;
if (wbc->nr_to_write <= 0)
return 0;
wbc->for_writepages = 1;
if (mapping->a_ops->writepages)
[PATCH] mm: tracking shared dirty pages Tracking of dirty pages in shared writeable mmap()s. The idea is simple: write protect clean shared writeable pages, catch the write-fault, make writeable and set dirty. On page write-back clean all the PTE dirty bits and write protect them once again. The implementation is a tad harder, mainly because the default backing_dev_info capabilities were too loosely maintained. Hence it is not enough to test the backing_dev_info for cap_account_dirty. The current heuristic is as follows, a VMA is eligible when: - its shared writeable (vm_flags & (VM_WRITE|VM_SHARED)) == (VM_WRITE|VM_SHARED) - it is not a 'special' mapping (vm_flags & (VM_PFNMAP|VM_INSERTPAGE)) == 0 - the backing_dev_info is cap_account_dirty mapping_cap_account_dirty(vma->vm_file->f_mapping) - f_op->mmap() didn't change the default page protection Page from remap_pfn_range() are explicitly excluded because their COW semantics are already horrid enough (see vm_normal_page() in do_wp_page()) and because they don't have a backing store anyway. mprotect() is taught about the new behaviour as well. However it overrides the last condition. Cleaning the pages on write-back is done with page_mkclean() a new rmap call. It can be called on any page, but is currently only implemented for mapped pages, if the page is found the be of a VMA that accounts dirty pages it will also wrprotect the PTE. Finally, in fs/buffers.c:try_to_free_buffers(); remove clear_page_dirty() from under ->private_lock. This seems to be safe, since ->private_lock is used to serialize access to the buffers, not the page itself. This is needed because clear_page_dirty() will call into page_mkclean() and would thereby violate locking order. [dhowells@redhat.com: Provide a page_mkclean() implementation for NOMMU] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Hugh Dickins <hugh@veritas.com> Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-09-26 06:30:57 +00:00
ret = mapping->a_ops->writepages(mapping, wbc);
else
ret = generic_writepages(mapping, wbc);
wbc->for_writepages = 0;
return ret;
}
/**
* write_one_page - write out a single page and optionally wait on I/O
* @page: the page to write
* @wait: if true, wait on writeout
*
* The page must be locked by the caller and will be unlocked upon return.
*
* write_one_page() returns a negative error code if I/O failed.
*/
int write_one_page(struct page *page, int wait)
{
struct address_space *mapping = page->mapping;
int ret = 0;
struct writeback_control wbc = {
.sync_mode = WB_SYNC_ALL,
.nr_to_write = 1,
};
BUG_ON(!PageLocked(page));
if (wait)
wait_on_page_writeback(page);
if (clear_page_dirty_for_io(page)) {
page_cache_get(page);
ret = mapping->a_ops->writepage(page, &wbc);
if (ret == 0 && wait) {
wait_on_page_writeback(page);
if (PageError(page))
ret = -EIO;
}
page_cache_release(page);
} else {
unlock_page(page);
}
return ret;
}
EXPORT_SYMBOL(write_one_page);
/*
* For address_spaces which do not use buffers nor write back.
*/
int __set_page_dirty_no_writeback(struct page *page)
{
if (!PageDirty(page))
SetPageDirty(page);
return 0;
}
/*
* For address_spaces which do not use buffers. Just tag the page as dirty in
* its radix tree.
*
* This is also used when a single buffer is being dirtied: we want to set the
* page dirty in that case, but not all the buffers. This is a "bottom-up"
* dirtying, whereas __set_page_dirty_buffers() is a "top-down" dirtying.
*
* Most callers have locked the page, which pins the address_space in memory.
* But zap_pte_range() does not lock the page, however in that case the
* mapping is pinned by the vma's ->vm_file reference.
*
* We take care to handle the case where the page was truncated from the
* mapping by re-checking page_mapping() insode tree_lock.
*/
int __set_page_dirty_nobuffers(struct page *page)
{
if (!TestSetPageDirty(page)) {
struct address_space *mapping = page_mapping(page);
struct address_space *mapping2;
if (!mapping)
return 1;
write_lock_irq(&mapping->tree_lock);
mapping2 = page_mapping(page);
if (mapping2) { /* Race with truncate? */
BUG_ON(mapping2 != mapping);
WARN_ON_ONCE(!PagePrivate(page) && !PageUptodate(page));
if (mapping_cap_account_dirty(mapping)) {
__inc_zone_page_state(page, NR_FILE_DIRTY);
task_io_account_write(PAGE_CACHE_SIZE);
}
radix_tree_tag_set(&mapping->page_tree,
page_index(page), PAGECACHE_TAG_DIRTY);
}
write_unlock_irq(&mapping->tree_lock);
if (mapping->host) {
/* !PageAnon && !swapper_space */
__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
}
return 1;
}
return 0;
}
EXPORT_SYMBOL(__set_page_dirty_nobuffers);
/*
* When a writepage implementation decides that it doesn't want to write this
* page for some reason, it should redirty the locked page via
* redirty_page_for_writepage() and it should then unlock the page and return 0
*/
int redirty_page_for_writepage(struct writeback_control *wbc, struct page *page)
{
wbc->pages_skipped++;
return __set_page_dirty_nobuffers(page);
}
EXPORT_SYMBOL(redirty_page_for_writepage);
/*
* If the mapping doesn't provide a set_page_dirty a_op, then
* just fall through and assume that it wants buffer_heads.
*/
int fastcall set_page_dirty(struct page *page)
{
struct address_space *mapping = page_mapping(page);
if (likely(mapping)) {
int (*spd)(struct page *) = mapping->a_ops->set_page_dirty;
[PATCH] BLOCK: Make it possible to disable the block layer [try #6] Make it possible to disable the block layer. Not all embedded devices require it, some can make do with just JFFS2, NFS, ramfs, etc - none of which require the block layer to be present. This patch does the following: (*) Introduces CONFIG_BLOCK to disable the block layer, buffering and blockdev support. (*) Adds dependencies on CONFIG_BLOCK to any configuration item that controls an item that uses the block layer. This includes: (*) Block I/O tracing. (*) Disk partition code. (*) All filesystems that are block based, eg: Ext3, ReiserFS, ISOFS. (*) The SCSI layer. As far as I can tell, even SCSI chardevs use the block layer to do scheduling. Some drivers that use SCSI facilities - such as USB storage - end up disabled indirectly from this. (*) Various block-based device drivers, such as IDE and the old CDROM drivers. (*) MTD blockdev handling and FTL. (*) JFFS - which uses set_bdev_super(), something it could avoid doing by taking a leaf out of JFFS2's book. (*) Makes most of the contents of linux/blkdev.h, linux/buffer_head.h and linux/elevator.h contingent on CONFIG_BLOCK being set. sector_div() is, however, still used in places, and so is still available. (*) Also made contingent are the contents of linux/mpage.h, linux/genhd.h and parts of linux/fs.h. (*) Makes a number of files in fs/ contingent on CONFIG_BLOCK. (*) Makes mm/bounce.c (bounce buffering) contingent on CONFIG_BLOCK. (*) set_page_dirty() doesn't call __set_page_dirty_buffers() if CONFIG_BLOCK is not enabled. (*) fs/no-block.c is created to hold out-of-line stubs and things that are required when CONFIG_BLOCK is not set: (*) Default blockdev file operations (to give error ENODEV on opening). (*) Makes some /proc changes: (*) /proc/devices does not list any blockdevs. (*) /proc/diskstats and /proc/partitions are contingent on CONFIG_BLOCK. (*) Makes some compat ioctl handling contingent on CONFIG_BLOCK. (*) If CONFIG_BLOCK is not defined, makes sys_quotactl() return -ENODEV if given command other than Q_SYNC or if a special device is specified. (*) In init/do_mounts.c, no reference is made to the blockdev routines if CONFIG_BLOCK is not defined. This does not prohibit NFS roots or JFFS2. (*) The bdflush, ioprio_set and ioprio_get syscalls can now be absent (return error ENOSYS by way of cond_syscall if so). (*) The seclvl_bd_claim() and seclvl_bd_release() security calls do nothing if CONFIG_BLOCK is not set, since they can't then happen. Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2006-09-30 18:45:40 +00:00
#ifdef CONFIG_BLOCK
if (!spd)
spd = __set_page_dirty_buffers;
#endif
return (*spd)(page);
}
if (!PageDirty(page)) {
if (!TestSetPageDirty(page))
return 1;
}
return 0;
}
EXPORT_SYMBOL(set_page_dirty);
/*
* set_page_dirty() is racy if the caller has no reference against
* page->mapping->host, and if the page is unlocked. This is because another
* CPU could truncate the page off the mapping and then free the mapping.
*
* Usually, the page _is_ locked, or the caller is a user-space process which
* holds a reference on the inode by having an open file.
*
* In other cases, the page should be locked before running set_page_dirty().
*/
int set_page_dirty_lock(struct page *page)
{
int ret;
lock_page_nosync(page);
ret = set_page_dirty(page);
unlock_page(page);
return ret;
}
EXPORT_SYMBOL(set_page_dirty_lock);
/*
* Clear a page's dirty flag, while caring for dirty memory accounting.
* Returns true if the page was previously dirty.
*
* This is for preparing to put the page under writeout. We leave the page
* tagged as dirty in the radix tree so that a concurrent write-for-sync
* can discover it via a PAGECACHE_TAG_DIRTY walk. The ->writepage
* implementation will run either set_page_writeback() or set_page_dirty(),
* at which stage we bring the page's dirty flag and radix-tree dirty tag
* back into sync.
*
* This incoherency between the page's dirty flag and radix-tree tag is
* unfortunate, but it only exists while the page is locked.
*/
int clear_page_dirty_for_io(struct page *page)
{
struct address_space *mapping = page_mapping(page);
BUG_ON(!PageLocked(page));
mm: share PG_readahead and PG_reclaim Share the same page flag bit for PG_readahead and PG_reclaim. One is used only on file reads, another is only for emergency writes. One is used mostly for fresh/young pages, another is for old pages. Combinations of possible interactions are: a) clear PG_reclaim => implicit clear of PG_readahead it will delay an asynchronous readahead into a synchronous one it actually does _good_ for readahead: the pages will be reclaimed soon, it's readahead thrashing! in this case, synchronous readahead makes more sense. b) clear PG_readahead => implicit clear of PG_reclaim one(and only one) page will not be reclaimed in time it can be avoided by checking PageWriteback(page) in readahead first c) set PG_reclaim => implicit set of PG_readahead will confuse readahead and make it restart the size rampup process it's a trivial problem, and can mostly be avoided by checking PageWriteback(page) first in readahead d) set PG_readahead => implicit set of PG_reclaim PG_readahead will never be set on already cached pages. PG_reclaim will always be cleared on dirtying a page. so not a problem. In summary, a) we get better behavior b,d) possible interactions can be avoided c) racy condition exists that might affect readahead, but the chance is _really_ low, and the hurt on readahead is trivial. Compound pages also use PG_reclaim, but for now they do not interact with reclaim/readahead code. Signed-off-by: Fengguang Wu <wfg@mail.ustc.edu.cn> Cc: Rusty Russell <rusty@rustcorp.com.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-19 08:48:07 +00:00
ClearPageReclaim(page);
VM: Fix nasty and subtle race in shared mmap'ed page writeback The VM layer (on the face of it, fairly reasonably) expected that when it does a ->writepage() call to the filesystem, it would write out the full page at that point in time. Especially since it had earlier marked the whole page dirty with "set_page_dirty()". But that isn't actually the case: ->writepage() does not actually write a page, it writes the parts of the page that have been explicitly marked dirty before, *and* that had not got written out for other reasons since the last time we told it they were dirty. That last caveat is the important one. Which _most_ of the time ends up being the whole page (since we had called "set_page_dirty()" on the page earlier), but if the filesystem had done any dirty flushing of its own (for example, to honor some internal write ordering guarantees), it might end up doing only a partial page IO (or none at all) when ->writepage() is actually called. That is the correct thing in general (since we actually often _want_ only the known-dirty parts of the page to be written out), but the shared dirty page handling had implicitly forgotten about these details, and had a number of cases where it was doing just the "->writepage()" part, without telling the low-level filesystem that the whole page might have been re-dirtied as part of being mapped writably into user space. Since most of the time the FS did actually write out the full page, we didn't notice this for a loong time, and this needed some really odd patterns to trigger. But it caused occasional corruption with rtorrent and with the Debian "apt" database, because both use shared mmaps to update the end result. This fixes it. Finally. After way too much hair-pulling. Acked-by: Nick Piggin <nickpiggin@yahoo.com.au> Acked-by: Martin J. Bligh <mbligh@google.com> Acked-by: Martin Michlmayr <tbm@cyrius.com> Acked-by: Martin Johansson <martin@fatbob.nu> Acked-by: Ingo Molnar <mingo@elte.hu> Acked-by: Andrei Popa <andrei.popa@i-neo.ro> Cc: High Dickins <hugh@veritas.com> Cc: Andrew Morton <akpm@osdl.org>, Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Segher Boessenkool <segher@kernel.crashing.org> Cc: David Miller <davem@davemloft.net> Cc: Arjan van de Ven <arjan@infradead.org> Cc: Gordon Farquharson <gordonfarquharson@gmail.com> Cc: Guillaume Chazarain <guichaz@yahoo.fr> Cc: Theodore Tso <tytso@mit.edu> Cc: Kenneth Cheng <kenneth.w.chen@intel.com> Cc: Tobias Diedrich <ranma@tdiedrich.de> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-12-29 18:00:58 +00:00
if (mapping && mapping_cap_account_dirty(mapping)) {
/*
* Yes, Virginia, this is indeed insane.
*
* We use this sequence to make sure that
* (a) we account for dirty stats properly
* (b) we tell the low-level filesystem to
* mark the whole page dirty if it was
* dirty in a pagetable. Only to then
* (c) clean the page again and return 1 to
* cause the writeback.
*
* This way we avoid all nasty races with the
* dirty bit in multiple places and clearing
* them concurrently from different threads.
*
* Note! Normally the "set_page_dirty(page)"
* has no effect on the actual dirty bit - since
* that will already usually be set. But we
* need the side effects, and it can help us
* avoid races.
*
* We basically use the page "master dirty bit"
* as a serialization point for all the different
* threads doing their things.
*/
if (page_mkclean(page))
set_page_dirty(page);
/*
* We carefully synchronise fault handlers against
* installing a dirty pte and marking the page dirty
* at this point. We do this by having them hold the
* page lock at some point after installing their
* pte, but before marking the page dirty.
* Pages are always locked coming in here, so we get
* the desired exclusion. See mm/memory.c:do_wp_page()
* for more comments.
*/
VM: Fix nasty and subtle race in shared mmap'ed page writeback The VM layer (on the face of it, fairly reasonably) expected that when it does a ->writepage() call to the filesystem, it would write out the full page at that point in time. Especially since it had earlier marked the whole page dirty with "set_page_dirty()". But that isn't actually the case: ->writepage() does not actually write a page, it writes the parts of the page that have been explicitly marked dirty before, *and* that had not got written out for other reasons since the last time we told it they were dirty. That last caveat is the important one. Which _most_ of the time ends up being the whole page (since we had called "set_page_dirty()" on the page earlier), but if the filesystem had done any dirty flushing of its own (for example, to honor some internal write ordering guarantees), it might end up doing only a partial page IO (or none at all) when ->writepage() is actually called. That is the correct thing in general (since we actually often _want_ only the known-dirty parts of the page to be written out), but the shared dirty page handling had implicitly forgotten about these details, and had a number of cases where it was doing just the "->writepage()" part, without telling the low-level filesystem that the whole page might have been re-dirtied as part of being mapped writably into user space. Since most of the time the FS did actually write out the full page, we didn't notice this for a loong time, and this needed some really odd patterns to trigger. But it caused occasional corruption with rtorrent and with the Debian "apt" database, because both use shared mmaps to update the end result. This fixes it. Finally. After way too much hair-pulling. Acked-by: Nick Piggin <nickpiggin@yahoo.com.au> Acked-by: Martin J. Bligh <mbligh@google.com> Acked-by: Martin Michlmayr <tbm@cyrius.com> Acked-by: Martin Johansson <martin@fatbob.nu> Acked-by: Ingo Molnar <mingo@elte.hu> Acked-by: Andrei Popa <andrei.popa@i-neo.ro> Cc: High Dickins <hugh@veritas.com> Cc: Andrew Morton <akpm@osdl.org>, Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Segher Boessenkool <segher@kernel.crashing.org> Cc: David Miller <davem@davemloft.net> Cc: Arjan van de Ven <arjan@infradead.org> Cc: Gordon Farquharson <gordonfarquharson@gmail.com> Cc: Guillaume Chazarain <guichaz@yahoo.fr> Cc: Theodore Tso <tytso@mit.edu> Cc: Kenneth Cheng <kenneth.w.chen@intel.com> Cc: Tobias Diedrich <ranma@tdiedrich.de> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-12-29 18:00:58 +00:00
if (TestClearPageDirty(page)) {
dec_zone_page_state(page, NR_FILE_DIRTY);
VM: Fix nasty and subtle race in shared mmap'ed page writeback The VM layer (on the face of it, fairly reasonably) expected that when it does a ->writepage() call to the filesystem, it would write out the full page at that point in time. Especially since it had earlier marked the whole page dirty with "set_page_dirty()". But that isn't actually the case: ->writepage() does not actually write a page, it writes the parts of the page that have been explicitly marked dirty before, *and* that had not got written out for other reasons since the last time we told it they were dirty. That last caveat is the important one. Which _most_ of the time ends up being the whole page (since we had called "set_page_dirty()" on the page earlier), but if the filesystem had done any dirty flushing of its own (for example, to honor some internal write ordering guarantees), it might end up doing only a partial page IO (or none at all) when ->writepage() is actually called. That is the correct thing in general (since we actually often _want_ only the known-dirty parts of the page to be written out), but the shared dirty page handling had implicitly forgotten about these details, and had a number of cases where it was doing just the "->writepage()" part, without telling the low-level filesystem that the whole page might have been re-dirtied as part of being mapped writably into user space. Since most of the time the FS did actually write out the full page, we didn't notice this for a loong time, and this needed some really odd patterns to trigger. But it caused occasional corruption with rtorrent and with the Debian "apt" database, because both use shared mmaps to update the end result. This fixes it. Finally. After way too much hair-pulling. Acked-by: Nick Piggin <nickpiggin@yahoo.com.au> Acked-by: Martin J. Bligh <mbligh@google.com> Acked-by: Martin Michlmayr <tbm@cyrius.com> Acked-by: Martin Johansson <martin@fatbob.nu> Acked-by: Ingo Molnar <mingo@elte.hu> Acked-by: Andrei Popa <andrei.popa@i-neo.ro> Cc: High Dickins <hugh@veritas.com> Cc: Andrew Morton <akpm@osdl.org>, Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Segher Boessenkool <segher@kernel.crashing.org> Cc: David Miller <davem@davemloft.net> Cc: Arjan van de Ven <arjan@infradead.org> Cc: Gordon Farquharson <gordonfarquharson@gmail.com> Cc: Guillaume Chazarain <guichaz@yahoo.fr> Cc: Theodore Tso <tytso@mit.edu> Cc: Kenneth Cheng <kenneth.w.chen@intel.com> Cc: Tobias Diedrich <ranma@tdiedrich.de> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-12-29 18:00:58 +00:00
return 1;
}
VM: Fix nasty and subtle race in shared mmap'ed page writeback The VM layer (on the face of it, fairly reasonably) expected that when it does a ->writepage() call to the filesystem, it would write out the full page at that point in time. Especially since it had earlier marked the whole page dirty with "set_page_dirty()". But that isn't actually the case: ->writepage() does not actually write a page, it writes the parts of the page that have been explicitly marked dirty before, *and* that had not got written out for other reasons since the last time we told it they were dirty. That last caveat is the important one. Which _most_ of the time ends up being the whole page (since we had called "set_page_dirty()" on the page earlier), but if the filesystem had done any dirty flushing of its own (for example, to honor some internal write ordering guarantees), it might end up doing only a partial page IO (or none at all) when ->writepage() is actually called. That is the correct thing in general (since we actually often _want_ only the known-dirty parts of the page to be written out), but the shared dirty page handling had implicitly forgotten about these details, and had a number of cases where it was doing just the "->writepage()" part, without telling the low-level filesystem that the whole page might have been re-dirtied as part of being mapped writably into user space. Since most of the time the FS did actually write out the full page, we didn't notice this for a loong time, and this needed some really odd patterns to trigger. But it caused occasional corruption with rtorrent and with the Debian "apt" database, because both use shared mmaps to update the end result. This fixes it. Finally. After way too much hair-pulling. Acked-by: Nick Piggin <nickpiggin@yahoo.com.au> Acked-by: Martin J. Bligh <mbligh@google.com> Acked-by: Martin Michlmayr <tbm@cyrius.com> Acked-by: Martin Johansson <martin@fatbob.nu> Acked-by: Ingo Molnar <mingo@elte.hu> Acked-by: Andrei Popa <andrei.popa@i-neo.ro> Cc: High Dickins <hugh@veritas.com> Cc: Andrew Morton <akpm@osdl.org>, Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Segher Boessenkool <segher@kernel.crashing.org> Cc: David Miller <davem@davemloft.net> Cc: Arjan van de Ven <arjan@infradead.org> Cc: Gordon Farquharson <gordonfarquharson@gmail.com> Cc: Guillaume Chazarain <guichaz@yahoo.fr> Cc: Theodore Tso <tytso@mit.edu> Cc: Kenneth Cheng <kenneth.w.chen@intel.com> Cc: Tobias Diedrich <ranma@tdiedrich.de> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-12-29 18:00:58 +00:00
return 0;
}
VM: Fix nasty and subtle race in shared mmap'ed page writeback The VM layer (on the face of it, fairly reasonably) expected that when it does a ->writepage() call to the filesystem, it would write out the full page at that point in time. Especially since it had earlier marked the whole page dirty with "set_page_dirty()". But that isn't actually the case: ->writepage() does not actually write a page, it writes the parts of the page that have been explicitly marked dirty before, *and* that had not got written out for other reasons since the last time we told it they were dirty. That last caveat is the important one. Which _most_ of the time ends up being the whole page (since we had called "set_page_dirty()" on the page earlier), but if the filesystem had done any dirty flushing of its own (for example, to honor some internal write ordering guarantees), it might end up doing only a partial page IO (or none at all) when ->writepage() is actually called. That is the correct thing in general (since we actually often _want_ only the known-dirty parts of the page to be written out), but the shared dirty page handling had implicitly forgotten about these details, and had a number of cases where it was doing just the "->writepage()" part, without telling the low-level filesystem that the whole page might have been re-dirtied as part of being mapped writably into user space. Since most of the time the FS did actually write out the full page, we didn't notice this for a loong time, and this needed some really odd patterns to trigger. But it caused occasional corruption with rtorrent and with the Debian "apt" database, because both use shared mmaps to update the end result. This fixes it. Finally. After way too much hair-pulling. Acked-by: Nick Piggin <nickpiggin@yahoo.com.au> Acked-by: Martin J. Bligh <mbligh@google.com> Acked-by: Martin Michlmayr <tbm@cyrius.com> Acked-by: Martin Johansson <martin@fatbob.nu> Acked-by: Ingo Molnar <mingo@elte.hu> Acked-by: Andrei Popa <andrei.popa@i-neo.ro> Cc: High Dickins <hugh@veritas.com> Cc: Andrew Morton <akpm@osdl.org>, Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Segher Boessenkool <segher@kernel.crashing.org> Cc: David Miller <davem@davemloft.net> Cc: Arjan van de Ven <arjan@infradead.org> Cc: Gordon Farquharson <gordonfarquharson@gmail.com> Cc: Guillaume Chazarain <guichaz@yahoo.fr> Cc: Theodore Tso <tytso@mit.edu> Cc: Kenneth Cheng <kenneth.w.chen@intel.com> Cc: Tobias Diedrich <ranma@tdiedrich.de> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-12-29 18:00:58 +00:00
return TestClearPageDirty(page);
}
EXPORT_SYMBOL(clear_page_dirty_for_io);
int test_clear_page_writeback(struct page *page)
{
struct address_space *mapping = page_mapping(page);
int ret;
if (mapping) {
unsigned long flags;
write_lock_irqsave(&mapping->tree_lock, flags);
ret = TestClearPageWriteback(page);
if (ret)
radix_tree_tag_clear(&mapping->page_tree,
page_index(page),
PAGECACHE_TAG_WRITEBACK);
write_unlock_irqrestore(&mapping->tree_lock, flags);
} else {
ret = TestClearPageWriteback(page);
}
if (ret)
dec_zone_page_state(page, NR_WRITEBACK);
return ret;
}
int test_set_page_writeback(struct page *page)
{
struct address_space *mapping = page_mapping(page);
int ret;
if (mapping) {
unsigned long flags;
write_lock_irqsave(&mapping->tree_lock, flags);
ret = TestSetPageWriteback(page);
if (!ret)
radix_tree_tag_set(&mapping->page_tree,
page_index(page),
PAGECACHE_TAG_WRITEBACK);
if (!PageDirty(page))
radix_tree_tag_clear(&mapping->page_tree,
page_index(page),
PAGECACHE_TAG_DIRTY);
write_unlock_irqrestore(&mapping->tree_lock, flags);
} else {
ret = TestSetPageWriteback(page);
}
if (!ret)
inc_zone_page_state(page, NR_WRITEBACK);
return ret;
}
EXPORT_SYMBOL(test_set_page_writeback);
/*
* Return true if any of the pages in the mapping are marged with the
* passed tag.
*/
int mapping_tagged(struct address_space *mapping, int tag)
{
unsigned long flags;
int ret;
read_lock_irqsave(&mapping->tree_lock, flags);
ret = radix_tree_tagged(&mapping->page_tree, tag);
read_unlock_irqrestore(&mapping->tree_lock, flags);
return ret;
}
EXPORT_SYMBOL(mapping_tagged);